De Bruijn goes Neural: Causality-Aware Graph Neural Networks for Time Series Data on Dynamic Graphs

TL;DR

This paper introduces De Bruijn Graph Neural Networks (DBGNNs), a new architecture for modeling time-resolved data on dynamic graphs by capturing causal temporal patterns with higher-order De Bruijn graphs, improving node classification performance.

Contribution

The paper presents a novel GNN architecture that incorporates higher-order De Bruijn graphs to model causal temporal patterns in dynamic graphs, with a method for selecting the optimal graph order.

Findings

DBGNNs outperform baseline models in node classification tasks.

Statistical model selection effectively identifies optimal De Bruijn graph order.

The approach captures non-Markovian dynamics in temporal graph data.

Abstract

We introduce De Bruijn Graph Neural Networks (DBGNNs), a novel time-aware graph neural network architecture for time-resolved data on dynamic graphs. Our approach accounts for temporal-topological patterns that unfold in the causal topology of dynamic graphs, which is determined by causal walks, i.e. temporally ordered sequences of links by which nodes can influence each other over time. Our architecture builds on multiple layers of higher-order De Bruijn graphs, an iterative line graph construction where nodes in a De Bruijn graph of order k represent walks of length k-1, while edges represent walks of length k. We develop a graph neural network architecture that utilizes De Bruijn graphs to implement a message passing scheme that follows a non-Markovian dynamics, which enables us to learn patterns in the causal topology of a dynamic graph. Addressing the issue that De Bruijn graphs with different orders k can be used to model the same data set, we further apply statistical model selection to determine the optimal graph topology to be used for message passing. An evaluation in synthetic and empirical data sets suggests that DBGNNs can leverage temporal patterns in dynamic graphs, which substantially improves the performance in a supervised node classification task.